Tumor Burden Quantification via Shape and Texture Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current CT imaging technologies face challenges in visualizing and tracking small liver lesions and metastatic disease, particularly in distinguishing tumor boundaries and quantifying tumor burden, which is time-consuming and inefficient, especially when multiple lesions are present.
Innovation Solution
A system and method for quantifying a selected attribute of an image volume by processing datasets based on shape and texture to compute an index of aggregate responses, enabling the tracking of tumor burden changes across treatments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physicians manually identify and track each individual lesion to quantify tumor burden, then measurement precision is improved, but productivity deteriorates due to extreme time consumption
Solution Approach 1:
The patent segments the tumor burden quantification process into automated detection of individual lesions and aggregation into a total burden index. The system automatically identifies and tracks each lesion's volume across time points, then sums them to provide the total tumor burden, eliminating manual tracking while maintaining precision
Solution Approach 2:
The system performs self-service by automatically detecting, measuring, and tracking tumor lesions without requiring manual intervention. The automated algorithm processes image data, quantifies lesion volumes, and monitors changes over time, freeing physicians from time-consuming manual measurement
2Productivity
If CT imaging is used to visualize liver lesions, then productivity is improved through routine screening capability, but measurement precision deteriorates due to limited visual contrast
Solution Approach 1:
The patent changes the parameter used for tumor detection from visual contrast (intensity/HU values) to shape and texture attributes. The system extracts geometric parameters (volume, surface area, shape factors) and textural characteristics to identify and quantify lesions, overcoming CT's limited contrast capability
Solution Approach 2:
The system replaces the mechanical/visual perception mechanism with computational image processing. Instead of relying on human eye perception of contrast, the system uses automated algorithms to detect shape and texture patterns, substituting biological visualization with digital analysis
3Productivity
If automated algorithms are used to quantify tumor attributes, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent creates a universal image processing framework that can handle multiple tumor types and imaging modalities through a single cohesive system. The same algorithmic approach works for detecting various lesion types across different organs, providing multi-functionality that justifies the computational complexity
Solution Approach 2:
The system manages complexity by transforming the problem into parameter extraction rather than complex image analysis. By focusing on shape and texture parameters that can be derived through standardized mathematical operations, the system achieves automated quantification without requiring overly complex processing algorithms
Data Source
AI summary
Methods and systems for quantification of a selected attribute of an image volume are provided. The system is configured to receive an image dataset for a volume of interest, process the dataset for a selected attribute based at least on one of shape and texture to obtain a plurality of responses, and compute an index of an aggregate of a plurality of obtained responses.